Communications of the ACM
Learning in the presence of finitely or infinitely many irrelevant attributes
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Learning Boolean Functions in an Infinite Attribute Space
Machine Learning
Small-bias probability spaces: efficient constructions and applications
SIAM Journal on Computing
Learning with restricted focus of attention
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Cryptographic limitations on learning Boolean formulae and finite automata
Journal of the ACM (JACM)
Horn approximations of empirical data
Artificial Intelligence
Exact learning Boolean functions via the monotone theory
Information and Computation
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Knowledge compilation and theory approximation
Journal of the ACM (JACM)
Off-line reasoning for on-line efficiency: knowledge bases
Artificial Intelligence
Artificial Intelligence
Journal of the ACM (JACM)
Logical settings for concept-learning
Artificial Intelligence
Defaults and relevance in model-based reasoning
Artificial Intelligence - Special issue on relevance
Learning first order universal Horn expressions
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Machine Learning
Machine Learning
The complexity of theorem-proving procedures
STOC '71 Proceedings of the third annual ACM symposium on Theory of computing
Learning to reason the non monotonic case
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Learning cost-sensitive active classifiers
Artificial Intelligence
Learning from examples with unspecified attribute values
Information and Computation
Polynomial certificates for propositional classes
Information and Computation
Learning to assign degrees of belief in relational domains
Machine Learning
Polynomial certificates for propositional classes
Information and Computation
Learning to assign degrees of belief in relational domains
ILP'07 Proceedings of the 17th international conference on Inductive logic programming
Implicit learning of common sense for reasoning
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
| Hi-index | 0.00 |
The Learning to Reason framework combines the study of Learning andReasoning into a single task. Within it, learning is donespecifically for the purpose of reasoning with the learned knowledge.Computational considerations show that this is a useful paradigm; insome cases learning and reasoning problems that are intractable whenstudied separately become tractable when performed as a task ofLearning to Reason.In this paper we study Learning to Reason problems where theinteraction with the world supplies the learner only partialinformation in the form of partial assignments. Several naturalinterpretations of partial assignments are considered and learning andreasoning algorithms using these are developed. The results presented exhibit a tradeoff betweenlearnability, the strength of the oracles used in the interface, and the range ofreasoning queries the learner is guaranteed to answer correctly.